Train Support Vector Machine Classifiers Research Articles

A hierarchical parallel fusion framework for egocentric ADL recognition based on discernment frame partitioning and belief coarsening

Recently, egocentric activity recognition has become a major research area in pattern recognition and artificial intelligence due to its high significance in potential applications in medical care, rehabilitation, smart home/office, etc. In this study, we develop a hierarchical parallel multimodal fusion framework for the recognition of egocentric activities in daily living (ADL). This framework uses the Dezert–Smarandache theory and is constructed around three modalities: location, motion and vision data from a wearable hybrid sensor system. The reciprocal distance and a trained support vector machine classifier are used to form the basic belief assignments (BBA) of location and motion. For vision data composed of egocentric photo streams, a well-trained convolutional neural network is utilized to produce a set of textual tags and the entropy-based statistics for these tags are used to construct the vision BBA. Discernment partitioning and belief coarsening theory are adopted for the hierarchical fusion of the three BBA functions from different ADL levels. Experimental results show that the recognition accuracy of the proposed fusion method was significantly higher than that of the methods based on single modality or modality combinations when our method was applied to real-life multimodal egocentric activity datasets. In addition, our method also achieved higher adaptability and scalability.

Islanding detection method based on image classification technique using histogram of oriented gradient features

A new islanding detection method based on image classification with support vector machine is proposed in this study. Histogram of oriented gradient features is extracted from the image for classifying non-islanding and islanding events. In the proposed technique, the time-series signal acquired from the point of common coupling is first converted into an image. Histogram of oriented gradient features is extracted from the image, which is used as an input feature vector for training and testing multiple support vector machine classifiers. Parameters such as voltage, rate of change of voltage, and rate of change of negative sequence voltage are used. Furthermore, a feature for early islanding detection is also presented to detect an islanding event even before it has occurred. The detection accuracy of the proposed method is tested with different kernels. The performance of all the classifiers is tested with 5-fold cross-validation. The classification results show that islanding detection with image classification based on the histogram of oriented gradient feature and multiple support vector machine classifiers can achieve excellent results.

Privacy-Preserving Outsourced Support Vector Machine Design for Secure Drug Discovery

In this paper, we propose a framework for privacy-preserving outsourced drug discovery in the cloud, which we refer to as POD. Specifically, POD is designed to allow the cloud to securely use multiple drug formula providers’ drug formulas to train Support Vector Machine (SVM) provided by the analytical model provider. In our approach, we design secure computation protocols to allow the cloud server to perform commonly used integer and fraction computations. To securely train the SVM, we design a secure SVM parameter selection protocol to select two SVM parameters and construct a secure sequential minimal optimization protocol to privately refresh both selected SVM parameters. The trained SVM classifier can be used to determine whether a drug chemical compound is active or not in a privacy-preserving way. Lastly, we prove that the proposed POD achieves the goal of SVM training and chemical compound classification without privacy leakage to unauthorized parties, as well as demonstrating its utility and efficiency using three real-world drug datasets.

Motor imagery EEG classification based on ensemble support vector learning

Background and Objective: Brain-computer interfaces build a communication pathway from the human brain to a computer. Motor imagery-based electroencephalogram (EEG) classification is a widely applied paradigm in brain-computer interfaces. The common spatial pattern, based on the event-related desynchronization (ERD)/event-related synchronization (ERS) phenomenon, is one of the most popular algorithms for motor imagery-based EEG classification. Moreover, the spatiotemporal discrepancy feature based on the event-related potential phenomenon has been demonstrated to provide complementary information to ERD/ERS-based features. In this paper, aiming to improve the performance of motor imagery-based EEG classification in a few-channel situation, an ensemble support vector learning (ESVL)-based approach is proposed to combine the advantages of the ERD/ERS-based features and the event-related potential-based features in motor imagery-based EEG classification.Methods: ESVL is an ensemble learning algorithm based on support vector machine classifier. Specifically, the decision boundary with the largest interclass margin is obtained using the support vector machine algorithm, and the distances between sample points and the decision boundary are mapped to posterior probabilities. The probabilities obtained from different support vector machine classifiers are combined to make prediction. Thus, ESVL leverages the advantages of multiple trained support vector machine classifiers and makes a better prediction based on the posterior probabilities. The class discrepancy-guided sub-band-based common spatial pattern and the spatiotemporal discrepancy feature are applied to extract discriminative features, and then, the extracted features are used to train the ESVL classifier and make predictions.Results: The BCI Competition IV datasets 2a and 2b are employed to evaluate the performance of the proposed ESVL algorithm. Experimental comparisons with the state-of-the-art methods are performed, and the proposed ESVL-based approach achieves an average max kappa value of 0.60 and 0.71 on BCI Competition IV datasets 2a and 2b respectively. The results show that the proposed ESVL-based approach improves the performance of motor imagery-based brain-computer interfaces.Conclusion: The proposed ESVL classifier could use the posterior probabilities to realize ensemble learning and the ESVL-based motor imagery classification approach takes advantage of the merits of ERD/ERS based feature and event-related potential based feature to improve the experimental performance.

Bagging based ensemble of Support Vector Machines with improved elitist GA-SVM features selection for cardiac arrhythmia classification

In this study, we proposed a robust model to classify ECG arrhythmia. The proposed approach has two stages: (1) generation of an optimal feature subset using GA and (2) the classification and evaluation of the reduced ECG arrhythmia data using SVM Ensemble with Bagging (bootstrap aggregating). In s tep one, We explored a novel Genetic Algorithm wrapped Soft Margin Support Vector Machine algorithm to produce the optimal subset of features set. This step greatly improved the quality of classification by eliminating irrelevant features. In Step two, we used the ensemble of SVM with bagging (bootstrap aggregating). We trained every single Support Vector Machine Classifier separately using the randomly chosen samples from training dataset through a bootstrap technique. Then, these individually trained Support Vector Machine Classifiers are aggregated using the double-layer hierarchical combining to produce a joint decision. To evaluate performance and effectiveness, we applied the proposed model on UCI Arrhythmia (standard 12 lead ECG signal recordings) data set to classify arrhythmia into normal and abnormal subjects. With the proposed model, we got a promising true classification accuracy rate. The method is also comparable with state of art classifiers and other methods present in the related literature. The outcomes of the experiment and statistical analysis pointed out that our model is a very useful and practical approach for ECG arrhythmia classification.

The Difficulty of German Information Booklets on Psoriasis and Psoriatic Arthritis: Automated Readability and Vocabulary Analysis

BackgroundInformation-seeking Psoriasis or Psoriatic Arthritis patients are confronted with numerous educational materials when looking through the internet. Literature suggests that only 17.0-21.4% (Psoriasis, Psoriatic Arthritis) of patients have a good level of knowledge about psoriasis treatment and self-management. A study from 1994 found that English Psoriasis/Psoriatic Arthritis brochures required a reading level between grades 8-12 to be understandable, which was confirmed in a follow-up study 20 years later. As readability of written health-related text material should not exceed the sixth-grade level, Psoriasis/Psoriatic Arthritis material seems to be ill-suited to its target audience. However, no data is available on the readability levels of Psoriasis/Psoriatic Arthritis brochures for German-speaking patients, and both the volume and their scope are unclear.ObjectiveThis study aimed to analyze freely available educational materials for Psoriasis/Psoriatic Arthritis patients written in German, quantifying their difficulty by assessing both the readability and the vocabulary used in the collected brochures.MethodsData collection was conducted manually via an internet search engine for Psoriasis/Psoriatic Arthritis–specific material, published as PDF documents. Next, raw text was extracted, and a computer-based readability and vocabulary analysis was performed on each brochure. For the readability analysis, we applied the Flesch Reading Ease (FRE) metric adapted for the German language, and the fourth Vienna formula (WSTF). To assess the laymen-friendliness of the vocabulary, the computation of an expert level was conducted using a specifically trained Support Vector Machine classifier. A two-sided, two-sample Wilcoxon test was applied to test whether the difficulty of brochures of pair-wise topic groups was different from each other.ResultsIn total, n=68 brochures were included for readability assessment, of which 71% (48/68) were published by pharmaceutical companies, 22% (15/68) by nonprofit organizations, and 7% (5/68) by public institutions. The collection was separated into four topic groups: basic information on Psoriasis/Psoriatic Arthritis (G1/G2), lifestyle, and behavior with Psoriasis/Psoriatic Arthritis (G3/G4), medication and therapy guidance (G5), and other topics (G6). On average, readability levels were comparatively low, with FRE=31.58 and WSTF=11.84. However, two-thirds of the educational materials (69%; 47/68) achieved a vocabulary score ≦4 (ie, easy, very easy) and were, therefore, suitable for a lay audience. Statistically significant differences between brochure groups G1 and G3 for FRE (P=.001), WSTF (P=.003), and vocabulary measure (L) (P=.01) exist, as do statistically significant differences for G2 and G4 in terms of FRE (P=.03), WSTF (P=.03) and L (P=.03).ConclusionsOnline Psoriasis/Psoriatic Arthritis patient education materials in German require, on average, a college or university education level. As a result, patients face barriers to understanding the available material, even though the vocabulary used seems appropriate. For this reason, publishers of Psoriasis/Psoriatic Arthritis brochures should carefully revise their educational materials to provide easier and more comprehensible information for patients with lower health literacy levels.

Comparison of Support Vector Machine and Random Forest Algorithms for Invasive and Expansive Species Classification Using Airborne Hyperspectral Data

Invasive and expansive plant species are considered a threat to natural biodiversity because of their high adaptability and low habitat requirements. Species investigated in this research, including Solidago spp., Calamagrostis epigejos, and Rubus spp., are successfully displacing native vegetation and claiming new areas, which in turn severely decreases natural ecosystem richness, as they rapidly encroach on protected areas (e.g., Natura 2000 habitats). Because of the damage caused, the European Union (EU) has committed all its member countries to monitor biodiversity. In this paper we compared two machine learning algorithms, Support Vector Machine (SVM) and Random Forest (RF), to identify Solidago spp., Calamagrostis epigejos, and Rubus spp. on HySpex hyperspectral aerial images. SVM and RF are reliable and well-known classifiers that achieve satisfactory results in the literature. Data sets containing 30, 50, 100, 200, and 300 pixels per class in the training data set were used to train SVM and RF classifiers. The classifications were performed on 430-spectral bands and on the most informative 30 bands extracted using the Minimum Noise Fraction (MNF) transformation. As a result, maps of the spatial distribution of analyzed species were achieved; high accuracies were observed for all data sets and classifiers (an average F1 score above 0.78). The highest accuracies were obtained using 30 MNF bands and 300 sample pixels per class in the training data set (average F1 score > 0.9). Lower training data set sample sizes resulted in decreased average F1 scores, up to 13 percentage points in the case of 30-pixel samples per class.

Prediction of peptide binding to MHC using machine learning with sequence and structure-based feature sets

Selecting peptides that bind strongly to the major histocompatibility complex (MHC) for inclusion in a vaccine has therapeutic potential for infections and tumors. Machine learning models trained on sequence data exist for peptide:MHC (p:MHC) binding predictions. Here, we train support vector machine classifier (SVMC) models on physicochemical sequence-based and structure-based descriptor sets to predict peptide binding to a well-studied model mouse MHC I allele, H-2Db. Recursive feature elimination and two-way forward feature selection were also performed. Although low on sensitivity compared to the current state-of-the-art algorithms, models based on physicochemical descriptor sets achieve specificity and precision comparable to the most popular sequence-based algorithms. The best-performing model is a hybrid descriptor set containing both sequence-based and structure-based descriptors. Interestingly, close to half of the physicochemical sequence-based descriptors remaining in the hybrid model were properties of the anchor positions, residues 5 and 9 in the peptide sequence. In contrast, residues flanking position 5 make little to no residue-specific contribution to the binding affinity prediction. The results suggest that machine-learned models incorporating both sequence-based descriptors and structural data may provide information on specific physicochemical properties determining binding affinities.

Detection of Spliced Image Forensics Using Texture Analysis of Median Filter Residual

In the image forensics, detection of Cut-Paste manipulation is complicated computing. In this paper, the texture analysis of the spliced image is used to detect image forensics. From the local entropy of the median filter residual (MFR) of the forged image, the feature set is extracted for the ground truth mask `Find Gray level regional Maxima (FGM),' and `Entropy-based Edge (EbE).' Also, from the local range, the feature set is extracted for ground truth mask {`Morphological-Open Image (MOI), and 'Morphological- Erosion Image (MOE)'}. The feature vector in this paper composed of the two MOIs, two MOEs, and one EbE. The defined novel feature vector trained on a cubic support vector machine (SVM) classifier for only the performance evaluation of the proposed scheme. The performance of the proposed image forensics detection (IFD) scheme was measured with the five transformed types of image: median filtered (window size: {3×3, 5×5}), JPEG compressed (quality factor: {90, 70}) and average filtered (window size: 3×3). For the detection of the spliced image forensics, the region of Cut-Paste is classified by an input image only to the proposed scheme without the need for the trained SVM classifier. Throughout the experiment, the accuracy of median filtering detection was 98% over. Also, The area under the curve by sensitivity (TP: true positive rate) and 1-specificity (FP: false positive rate) results of the proposed IFD scheme approached to `1' with the trained cubic SVM classifier. Experimental results show high efficiency and performance to the spliced image. Therefore, the grade evaluation of the proposed scheme is ``Excellent (A)”.

Leak detection in a gas pipeline using spectral portrait of acoustic emission signals

This paper proposes a reliable method to detect leaks and recognize their various sizes in a gas pipeline based on the spectral portrait of acoustic emission (AE) signals. Through analyzing the relation of leak syndromes and AE signals in the frequency domain, this paper demonstrates that leak identification only by signatures obtained from measured individual signals might be unreliable due to strong attenuation in wave propagation along pipelines. The proposed method constructs a vector quantity in the frequency domain from two AE signals simultaneously acquired by two sensor channels, combined with a wave propagation model. This quantity characterizes the spectral portrait of AE signals emitted from a leak, its signatures therefore reflect leakage syndromes the same as leak signals, whereas those of individual sensor-measurements involve considerable distortions. Hence, the accuracy and reliability of leak detection and recognition are improved by the approach using the spectral portrait-related quantity. This paper also describes bank filters designed to encode the spectral envelope of AE signals instead of observing their total continuous frequency span. Finally, a trained multi-class support vector machine (SVM) classifier is responsible for the leak categorization, exploiting a set of the most discriminative encoded spectral envelope (ESE) features. The experimental results show that the proposed method outperforms conventional algorithms in pattern separability quantified by Kullback-Leibler distance and classification accuracy.

MFL-Based Local Damage Diagnosis and SVM-Based Damage Type Classification for Wire Rope NDE.

Wire ropes used in various applications such as elevators and cranes to safely carry heavy weights are vulnerable to breakage or cross-sectional loss caused by the external environment. Such damage can pose a serious risk to the safety of the entire structure because damage under tensile force rapidly expands due to concentration of stress. In this study, the magnetic flux leakage (MFL) method was applied to diagnose cuts, corrosion, and compression damage in wire ropes. Magnetic flux signals were measured by scanning damaged wire rope specimens using a multi-channel sensor head and a compact data acquisition system. A series of signal-processing procedures, including the Hilbert transform-based enveloping process, was applied to reduce noise and improve the resolution of signals. The possibility of diagnosing several types of damage was verified using enveloped magnetic flux signals. The characteristics of the MFL signals according to each damage type were then analyzed by comparing the extracted damage indices for each damage type. For automated damage type classification, a support vector machine (SVM)-based classifier was trained using the extracted damage indices. Finally, damage types were automatically classified as cutting and other damages using the trained SVM classifier.

A Machine Vision Based Detection & Classification of Neovascularisation in Retinal Blood Vessels

Diabetic Retinopathy is an eye disease which is caused by excessive sugar level in blood. Insufficient secretion of insulin hormone is the ground for evolution of diabetes. It affects most of the important organs in our body. There are two types of DR: Non Proliferative Diabetic Retinopathy and Proliferative Diabetic Retinopathy. In this proposed system techniques are introduced to detect and classify neovascularisation. Input fundus image is preprocessed by median filtering and further new vessels are segmented by using Fuzzy c-means clustering algorithm. After segmentation SIFT features are extracted and are used to train support vector machine (SVM) classifier. This automated system has been tested for 70 fundus images and accuracy of 96% is achieved.

DFU_QUTNet: diabetic foot ulcer classification using novel deep convolutional neural network

Diabetic Foot Ulcer (DFU) is the main complication of Diabetes, which, if not properly treated, may lead to amputation. One of the approaches of DFU treatment depends on the attentiveness of clinicians and patients. This treatment approach has drawbacks such as the high cost of the diagnosis as well as the length of treatment. Although this approach gives powerful results, the need for a remote, cost-effective, and convenient DFU diagnosis approach is urgent. In this paper, we introduce a new dataset of 754-ft images which contain healthy skin and skin with a diabetic ulcer from different patients. A novel Deep Convolutional Neural Network, DFU_QUTNet, is also proposed for the automatic classification of normal skin (healthy skin) class versus abnormal skin (DFU) class. Stacking more layers to a traditional Convolutional Neural Network to make it very deep does not lead to better performance, instead leading to worse performance due to the gradient. Therefore, our proposed DFU_QUTNet network is designed based on the idea of increasing the width of the network while keeping the depth compared to the state-of-the-art networks. Our network has been proven to be very beneficial for gradient propagation, as the error can be back-propagated through multiple paths. It also helps to combine different levels of features at each step of the network. Features extracted by DFU_QUTNet network are used to train Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) classifiers. For the sake of comparison, we have fine-tuned then re-trained and tested three pre-trained deep learning networks (GoogleNet, VGG16, and AlexNet) for the same task. The proposed DFU_QUTNet network outperformed the state-of-the-art CNN networks by achieving the F1-score of 94.5%.

Automated characterization and classification of coronary atherosclerotic plaques for intravascular optical coherence tomography

Identification of coronary atherosclerotic plaques and vulnerable plaques is of great clinical significance in the diagnosis and treatment of coronary artery diseases, such as myocardial infarction and sudden death. Optical coherence tomography (OCT) is a catheter-based intracoronary imaging technique with high resolution (<20μm) adopted to study the morphology of atherosclerotic plaques and identification of the composition of plaques. Nevertheless, manual characterization and quantification of plaques by clinicians is a labor-intensive and subjective procedure. This study aimed to propose a novel plaque characterization algorithm to automatically characterize and classify the atherosclerotic plaques (fibrous, calcific, and lipid-rich). First, nongeometric features such as Fisher vector, principal component analysis, histogram of the oriented gradient, and local binary pattern were investigated and adapted to two geometric features (basic feature and texture feature) to characterize the plaques. Second, for automated classification of the plaques, a hard example mining strategy was introduced to train support vector machine classifier and improve the effectiveness of training data. Third, to demonstrate the relationship between the selected features and the plaque classification accuracy, different feature compositions and comparisons were presented. The contribution of key features to the final classification was revealed. Datasets from 20 OCT pullbacks of 9 patients were used in the training and testing using the proposed algorithm. The overall classification accuracy reached 96.8%, and that of fibrous, calcific, and lipid-rich plaques was 94%, 97.2%, and 99.2%, respectively.

Bimodal recognition of affective states with the features inspired from human visual and auditory perception system

AbstractIn this article, attention‐based mechanism with the enhancement on biologically inspired network for emotion recognition is proposed. Existing bio‐inspired models use multiscale and multiorientation architecture to gain discriminative power and to extract meticulous visual features. Prevailing HMAX model represents S2 layers by randomly selected prototype patches from training samples that increase the computational complexity and degrade the discerning ability. As eyes and mouth regions are the most powerful and reliable cues in determining facial emotions, they serve as the prototype patches for S2 layer in HMAX model. Audio code 4 book is constructed from mel‐frequency cepstral coefficients, temporal and spectral features processed by principal component analysis. Audio and video data features are fused to train support vector machine classifier. The attained results on eNTERFACE, surrey audio‐visual expressed emotion and acted facial expressions in the wild database datasets ascertain the efficiency of the proposed architecture for emotion recognition.

Robust RGB-D Camera and IMU Fusion-based Cooperative and Relative Close-range Localization for Multiple Turtle-inspired Amphibious Spherical Robots

In the narrow, submarine, unstructured environment, the present localization approaches, such as GPS measurement, dead-reckoning, acoustic positioning, artificial landmarks-based method, are hard to be used for multiple small-scale underwater robots. Therefore, this paper proposes a novel RGB-D camera and Inertial Measurement Unit (IMU) fusion-based cooperative and relative close-range localization approach for special environments, such as underwater caves. Owing to the rotation movement with zero-radius, the cooperative localization of Multiple Turtle-inspired Amphibious Spherical Robot (MTASRs) is realized. Firstly, we present an efficient Histogram of Oriented Gradient (HOG) and Color Names (CNs) fusion feature extracted from color images of TASRs. Then, by training Support Vector Machine (SVM) classifier with this fusion feature, an automatic recognition method of TASRs is developed. Secondly, RGB-D camera-based measurement model is obtained by the depth map. In order to realize the cooperative and relative close-range localization of MTASRs, the MTASRs model is established with RGB-D camera and IMU. Finally, the depth measurement in water is corrected and the efficiency of RGB-D camera for underwater application is validated. Then experiments of our proposed localization method with three robots were conducted and the results verified the feasibility of the proposed method for MTASRs.

Dysarthric speech classification from coded telephone speech using glottal features

This paper proposes a new dysarthric speech classification method from coded telephone speech using glottal features. The proposed method utilizes glottal features, which are efficiently estimated from coded telephone speech using a recently proposed deep neural net-based glottal inverse filtering method. Two sets of glottal features were considered: (1) time- and frequency-domain parameters and (2) parameters based on principal component analysis (PCA). In addition, acoustic features are extracted from coded telephone speech using the openSMILE toolkit. The proposed method utilizes both acoustic and glottal features extracted from coded speech utterances and their corresponding dysarthric/healthy labels to train support vector machine classifiers. Separate classifiers are trained using both individual, and the combination of glottal and acoustic features. The coded telephone speech used in the experiments is generated using the adaptive multi-rate codec, which operates in two transmission bandwidths: narrowband (300 Hz - 3.4 kHz) and wideband (50 Hz - 7 kHz). The experiments were conducted using dysarthric and healthy speech utterances of the TORGO and universal access speech (UA-Speech) databases. Classification accuracy results indicated the effectiveness of glottal features in the identification of dysarthria from coded telephone speech. The results also showed that the glottal features in combination with the openSMILE-based acoustic features resulted in improved classification accuracies, which validate the complementary nature of glottal features. The proposed dysarthric speech classification method can potentially be employed in telemonitoring application for identifying the presence of dysarthria from coded telephone speech.

SPRINT-Gly: predicting N- and O-linked glycosylation sites of human and mouse proteins by using sequence and predicted structural properties.

Protein glycosylation is one of the most abundant post-translational modifications that plays an important role in immune responses, intercellular signaling, inflammation and host-pathogen interactions. However, due to the poor ionization efficiency and microheterogeneity of glycopeptides identifying glycosylation sites is a challenging task, and there is a demand for computational methods. Here, we constructed the largest dataset of human and mouse glycosylation sites to train deep learning neural networks and support vector machine classifiers to predict N-/O-linked glycosylation sites, respectively. The method, called SPRINT-Gly, achieved consistent results between ten-fold cross validation and independent test for predicting human and mouse glycosylation sites. For N-glycosylation, a mouse-trained model performs equally well in human glycoproteins and vice versa, however, due to significant differences in O-linked sites separate models were generated. Overall, SPRINT-Gly is 18% and 50% higher in Matthews correlation coefficient than the next best method compared in N-linked and O-linked sites, respectively. This improved performance is due to the inclusion of novel structure and sequence-based features. http://sparks-lab.org/server/SPRINT-Gly/. Supplementary data are available at Bioinformatics online.

Learning from Failure: Predicting Electronic Structure Calculation Outcomes with Machine Learning Models.

High-throughput computational screening for chemical discovery mandates the automated and unsupervised simulation of thousands of new molecules and materials. In challenging materials spaces, such as open shell transition metal chemistry, characterization requires time-consuming first-principles simulation that often necessitates human intervention. These calculations can frequently lead to a null result, e.g., the calculation does not converge or the molecule does not stay intact during a geometry optimization. To overcome this challenge toward realizing fully automated chemical discovery in transition metal chemistry, we have developed the first machine learning models that predict the likelihood of successful simulation outcomes. We train support vector machine and artificial neural network classifiers to predict simulation outcomes (i.e., geometry optimization result and degree of ⟨ S2⟩ deviation) for a chosen electronic structure method based on chemical composition. For these static models, we achieve an area under the curve of at least 0.95, minimizing computational time spent on nonproductive simulations and therefore enabling efficient chemical space exploration. We introduce a metric of model uncertainty based on the distribution of points in the latent space to systematically improve model prediction confidence. In a complementary approach, we train a convolutional neural network classification model on simulation output electronic and geometric structure time series data. This dynamic model generalizes more readily than the static classifier by becoming more predictive as input simulation length increases. Finally, we describe approaches for using these models to enable autonomous job control in transition metal complex discovery.

Multimodal framework based on audio‐visual features for summarisation of cricket videos

Sports broadcasters generate an enormous amount of video content on the cyberspace due to massive viewership all over the world. Analysis and consumption of this huge repository urges the broadcasters to apply video summarisation to extract the exciting segments from the entire video to capture user's interest and reap the storage and transmission benefits. Therefore, in this study an automatic method for key-events detection and summarisation based on audio-visual features is presented for cricket videos. Acoustic local binary pattern features are used to capture excitement level in the audio stream, which is used to train a binary support vector machine (SVM) classifier. Trained SVM classifier is used to label audio frame as an excited or non-excited frame. Excited audio frames are used to select candidate key-video frames. A decision tree-based classifier is trained to detect key-events in the input cricket videos that are then used for video summarisation. Performance of the proposed framework has been evaluated on a diverse dataset of cricket videos belonging to different tournaments and broadcasters. Experimental results indicate that the proposed method achieves an average accuracy of 95.5%, which signifies its effectiveness.